© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5958
    Prev
    Next
    INDEX
    Explanations

    groundwater discharge analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬ¼
    -0.12
    å¾Ĺ天
    -0.09
    scp
    -0.09
    å¼ĢçĽĺ
    -0.09
    iece
    -0.09
    iland
    -0.08
    achen
    -0.08
    ä¸ŃéĢĶ
    -0.08
    brick
    -0.08
    èĭĶ
    -0.08
    POSITIVE LOGITS
    fault
    0.08
    åħħåĢ¼
    0.08
    bounds
    0.08
    åıµ
    0.08
     Fathers
    0.08
    ream
    0.08
    edium
    0.08
    å·¥åİĤ
    0.08
    fen
    0.08
    enia
    0.08
    Activations Density 0.158%

    No Known Activations